Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation
Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing approach due to its ability to model high-fidelity spatial and temporal variations. However, existing methods suffer from substantial computational and memory overhead due to the redundant allocation of 4D Gaussians to static regions, which can also degrade image quality. In this work, we introduce hybrid 3D-4D Gaussian Splatting (3D-4DGS), a novel framework that adaptively represents static regions with 3D Gaussians while reserving 4D Gaussians for dynamic elements. Our method begins with a fully 4D Gaussian representation and iteratively converts temporally invariant Gaussians into 3D, significantly reducing the number of parameters and improving computational efficiency. Meanwhile, dynamic Gaussians retain their full 4D representation, capturing complex motions with high fidelity. Our approach achieves significantly faster training times compared to baseline 4D Gaussian Splatting methods while maintaining or improving the visual quality.
Code (1)
Tasks
3D Scene ReconstructionComputational EfficiencyNovel View SynthesisSimilar Papers 제목 키워드 기반
HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting
Rendering complex reflection of real-world scenes using 3D Gaussian splatting has been a quite promising solution for photorealistic novel view synthesis, but still faces bottlenecks especially in rendering speed and mem…
Novel View SynthesisLet it Snow! Animating Static Gaussian Scenes With Dynamic Weather Effects
3D Gaussian Splatting has recently enabled fast and photorealistic reconstruction of static 3D scenes. However, introducing dynamic elements that interact naturally with such static scenes remains challenging. Accordingl…
DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction
Dynamic scene reconstruction from monocular video is critical for real-world applications. This paper tackles the dual challenges of dynamic novel-view synthesis and 3D geometry reconstruction by introducing a hybrid fra…
3D geometry3D ReconstructionNovel View SynthesisReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficie…
Autonomous DrivingFully Explicit Dynamic Gaussian Splatting
3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not invol…
GPUNovel View Synthesis